Background and Objectives: The severity of acute pancreatitis (AP) is graded as mild (MAP), moderately severe (MSAP), and severe (SAP) according to the revised Atlanta Classification. Determining the severity of AP is the main goal in the early time of AP. The aim of this study was to compare laboratory parameters or indices including neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR) and neutrophil-creatinine index (NCI) at admission for predicting severity of AP. Materials and Methods: In this retrospective study, the data from patients who admitted with diagnosis of AP between January 2018 and December 2021 were collected. Laboratory parameters and indices including NLR, PLR and NCI were compared in the discrimination of AP severity groups. Results: A total of 421 patients [MAP group (n=213), MSAP group (n=158) and SAP group (n=50)] were included. WBC count, neutrophil count, hematocrit, CRP, BUN, creatinine, NLR and NCI were significant parameters to discriminate AP subgroups. The AUROC analysis for discriminating MSAP from MAP showed that WBC (AUC: 0.723, 95% CI: 0.674-0.768, p<0.001), hematocrit (AUC: 0.566, 95% CI: 0.514-0.607, p=0.032), NLR (AUC: 0.649, 95% CI: 0.598-0.698, p< 0.001) and NCI (AUC: 0.749, 95% CI: 0.701-0.792, p<0.001) were statistically significant parameters. Similarly, AUCs to discriminate SAP from MSAP were (AUC: 0.649, 95% CI: 0.579-0.713, p < 0.001) for WBC, (AUC: 0.703, 95% CI: 0.621-0.785, p< 0.001) for BUN, (AUC: 0.602, 95% CI: 0.532-0.669, p=0.029) for CRP and (AUC: 0.742, 95% CI: 0.676-0.800, p<0.001) for NCI. Logistic regression analyses indicated that NCI was the only parameter to discriminate MSAP form MAP (OR: 1.119, 95% CI: 1.015-1.235, p=0.023) and SAP from MSAP (OR: 1.113, 95% CI: 1.042-1.888, p = 0.001). Conclusions: The present study enabled the identification of neutrophil-creatinine index as a new prognostic tool for the assessment AP severity at hospital admission.

In this paper, a special recurrent neural network (RNN) called \emph{Long Short-Term Memory (LSTM)} is used to design a virtual load sensor that estimates the mass of heavy vehicles. The estimation algorithm consists of a two-layer LSTM network, with the two layers based on sequence-to-sequence and sequence-to-one logic, respectively. The network estimates the vehicle mass based on the vehicle speed, longitudinal acceleration, engine speed, engine torque, and the accelerator pedal position. The network is trained and tested with a data set collected in a high-fidelity simulation environment called Truckmaker. Training data is generated in acceleration maneuvers in a range of speeds whereas test data is obtained by simulating the vehicle in a Worldwide harmonized light vehicles test cycle (WLTC). Preliminary results show that, with the proposed approach, the heavy-vehicle mass can be estimated as accurately as commercial load sensors in a range of load mass as wide as four tons.

Background: Genome-wide association studies (GWAS) have shed light on various complex diseases and traits, by detecting more than 400,000 associated genetic loci. This number is expected to drastically increase because of the use of novel artificial intelligence methods offering new ways to study the effects of variants. Deep learning using artificial neural networks (ANN) is a sub-field of artificial intelligence, which simulates how the human brain learns. We aimed at assessing the potential of deep learning in human genetic studies of Alzheimer’s Disease (AD) and how these compare to the traditional statistical methods used in GWAS, by simultaneously testing the two approaches on the same dataset, while discovering new genetic loci associated to AD. Methods: To address this aim, phenotypic and genome-wide SNP data from the UK Biobank was analysed on a binary outcome, AD diagnosis, in two different data balance options, of one-to-one and one-to-two case-control datasets, using 2,764 cases vs 2,764 controls and 5,528 controls respectively matched on gender, age, ethnicity, PC1-20 and genotyping array. Genetic data handling and GWAS were performed using PLINK, whereas neural networks were trained using GenNet, a new ANN tool, with the same datasets, separated into training (60%), validation (20%) and test (20%) sets. Neural network layers were determined using biological knowledge, by annotating SNPs to genes and genes to AD related pathways, using ANNOVAR annotations followed by GeneSCF and KEGG. Results: Significant associations were detected between four SNPs linked to two different genes and AD for the 1 to 1 case-control study design and six SNPs linked to four different genes for the 1 to 2 case-control study design by using PLINK. All identified regions have been previously associated to AD. GenNet identified twelve SNPs on seven genes to be associated with AD, all with biological plausibility, achieving an AUC of 0.80 when using three biologically determined layers and 0.73 when using two layers at the neural networks. No common top SNPs were identified between the machine learning and GWAS models. Conclusion: This is one of the first studies attempting to compare the traditional GWAS to more sophisticated state-of-art methods for understanding the genetic architecture of complex phenotypes using the same dataset. More systematic comparisons with such approaches on real data are needed to enable best practises for machine learning in the analysis of genome-wide genetic data.

Citrus species essential oils (EOs) are significant sources of bioactive compounds and demonstrate diverse therapeutic effects. However, limited documentation exists regarding the phytochemicals associated with their biological activities. This study aims to assess the antioxidant activity, plant inhibitory properties, and brine shrimp cytotoxic effects of EOs derived from three Citrus species: C. sinensis, C. limon, and C. hystrix. Utilizing chemometric analysis and gas chromatography-mass spectrometry (GC-MS) fingerprints, the volatile components contributing to antioxidant activity were elucidated. The peels of the Citrus samples were hydro-distillated to obtain EOs, and subsequently subjected to antioxidant, plant inhibitory, and brine shrimp cytotoxic assays. The results indicated that C. limon EO exhibited the highest antioxidant activity, while C. hystrix and C. sinensis EOs demonstrated pronounced inhibitory effects against Aetrmia salina and Lactuca sativa, respectively. GC-MS analysis facilitated the identification of key compounds in each EO. Principal component analysis (PCA) and hierarchy cluster analysis (HCA) effectively categorized Citrus EOs based on their antioxidant properties, highlighting the proximity of C. limon and C. sinensis. Among the identified compounds, D-limonene, α-Terpineol, Caryophyllene, (+)-3-Carene, β-Pinene, (-)-Spathulenol, trans-p-Mentha-1(7),8-dien-2-ol, and trans-Verbenol were the most discriminating compounds affected the antioxidant activity of C.limon and C. sinensis EOs.

(1) Background: To fight for COVID-19 pandemic, immunity against SARS-CoV-2 should be achieved not only through natural infection but also vaccination. Controversies exist about the effect of COVID-19 vaccination on previously infected persons; (2) Methods: A prospective cohort was undergone to collect sera from unvaccinated survivors and vaccinated persons--with and without COVID-19 pre-infection. The sera were analyzed for the anti-Receptor Binding Domain (RBD) titers by ELISA and for the capacity to neutralize the pseudovirus of the Wuhan-Hu-1 strain by luciferase assays; (3) Results; Neither the antibody titers nor the neutralization capacity was significantly different between the three groups. However, the correlation between the antibody titers and the percentage of viral neutralization derived from sera of unvaccinated survivors was higher than that from vaccinated persons with pre-infection (Spearman correlation coefficient (r) = -0.8558; 95% CI, -0.9259 to -0.7288), p <0.0001 vs -0. 581; 95% CI, -0.7679 to -0.3028; p = 0.0002, respectively), indicating the capacity to neutralize the virus is better among the unvaccinated individuals. (4) Conclusions: Vaccines induced anti-RBD titers as high as the natural infection with lower neutralization capacity, and it did not boost the immunity in pre-infected persons.

Prosthetic device is designed to function as a replacement for a missing limb and typically consists of suspension, liner, socket, pylon and foot components. The objectives of this research are to design a pylon component of a transtibial prosthetics by implementing auxetic metamaterial and to also validate performance of the designed pylon under quasi-static and dynamic conditions. The design and analysis processes are conducted using the finite element analysis and its effectiveness is validated by experimental testing of the prototype pylon sample. In the design process, the pylon structure is formulated by rearranging 2D re-entrant hexagon model into 3D model. It is identified from the design evaluation that the pylon exhibits the stiffness of the value of 79.24, 2371.6, and 13344 kN/m for the ligament thickness variation of 0.3 mm, 1 mm, and 2 mm, respectively. This directly indicates a capability of the stiffness tuning of the pylon by changing the ligament thickness. It is evaluated that the pylon with the ligament thickness of 0.3 mm causes the deformation of 0.53 cm during a single period of gait cycle, while the ligament thickness of the 1 mm causes the deformation of 0.4 cm. The deformation physically indicates the energy absorption of the pylon structure and hence the thinner ligament, the higher energy absorption provides. It is also found from the deformation transition of the primary and secondary bends, the negative Poisson’s ratio is occurred in 3D model transformed from 2D re-entrant hexagon.